Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add ashfulcra/fulcra-tools --skill fulcra-agent-directivesgit clone --depth 1 https://github.com/ashfulcra/fulcra-toolsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/ashfulcra/fulcra-tools/fulcra-agent-directives)<a href="https://agentmods.dev/skills/ashfulcra/fulcra-tools/fulcra-agent-directives"><img src="https://agentmods.dev/badge/skills/ashfulcra/fulcra-tools/fulcra-agent-directives/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ashfulcra/fulcra-tools/fulcra-agent-directives"><img src="https://agentmods.dev/badge/skills/ashfulcra/fulcra-tools/fulcra-agent-directives.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00055 | $0.01706 |
| Opus 5 | $0.00028 | $0.00853 |
| Sonnet 5 | $0.00011 | $0.00341 |
| Haiku 4.5 | $0.00006 | $0.00171 |
Grade A, and why
fulcra-agent-directives scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fulcra Agent Directives
Enhances fulcra-agent-teams. Teams' native inbox is a
drop-zone of markdown files; this skill adds structured directed work: a directive IS a task with an
assignee, so it shows up in the reconcile views, carries priority + status machine, and has a
deterministic per-agent inbox with acks (acking hides an item for you and stops re-notify) —
without replacing the teams inbox for freeform messages.
Where to start — the re-entrancy probes
On waking (or before directing more work), probe your own inbox — what is already assigned to you and
unacked. Enter at the first probe that fails (per the repo's skill-quality pattern,
docs/skill-quality-pattern.md); reading the inbox is a pure fold and an ack is an idempotent
single-file write (acking an already-acked slug just rewrites the same shard), so re-entry is always
safe:
| Probe (run in order) | Command | Passes when | If it fails, enter at |
|---|---|---|---|
| Engine + auth usable? | coord-engine doctor <team> |
exits 0 and the last line is exactly doctor: healthy |
fix engine/auth first (see fulcra-agent-reconcile) — do NOT direct/ack against a broken engine |
| Inbox clear for me? | coord-engine inbox <team> -a <id> |
the header line ends 0 item(s) (the fold found nothing open + unacked for you) — NON-mutating read |
Work your inbox — the header names a non-zero count and each following line is an open directive; act on / ack it (inbox <team> --agent <id> --ack <slug>) via Verbs before directing new work |
Inbox clear → nothing is assigned to you and unacked; proceed to tell / broadcast / remind others,
or capture backlog with later. Add --all only for audit/debugging: it restores
acknowledged, closed, future, and @backlog history.
Verbs
All verbs below run as coord-engine <verb> …:
tell <team> <assignee> <title> [-p P0..P3] [-s summary] [-n next] [--from me] # direct work
broadcast <team> <title> … # assignee '*' — reaches every non-stale agent
remind <team> <assignee> <when> <title> … # hidden until WHEN (ISO or 5d/36h/10m)
later <team> <title> … # backlog (@backlog; inbox --all surfaces it)
intent <team> "<text>" --for user [--by <when>] # capture a spoken commitment (intent:user item)
inbox <team> [--agent X] [--json] # actionable directives for X
inbox <team> --agent X --all [--json] # full directed history
inbox <team> --agent X --ack <slug> # ack: hides it for X, stops re-notify
respond <team> <slug> --outcome TEXT [-e evidence] # record a response + close the loop
threads <team> --for <principal> [--json] # FOLD: dropped work-in-progress for a principal
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago Changed 40adf89cd066
- 11d ago First seen · 92 lines · 55 tokens per session scan A aacdb8f5683c
fulcra-agent-directives is a skill published in the GitHub repository ashfulcra/fulcra-tools (10 stars, last pushed yesterday), licensed MIT. It adds 55 tokens to every session and 1,706 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
meeting-action-items
Turn meeting notes into cited decisions, owners, tickets.
triage-issue
Intelligently triage bug reports and error messages by searching for duplicates in Jira and offering to create new issues or add comments to existing ones. When an agent needs to: (1) Triage a bug report or error message, (2) Check if an issue is a duplicate, (3) Find similar past issues, (4) Create a new bug ticket…
traction-eos
Implement the Entrepreneurial Operating System (EOS) to align vision and execution across a company. Use when the user mentions "EOS", "Entrepreneurial Operating System", "V/TO", "quarterly rocks", "Level 10 meetings", "accountability chart", "IDS process", "my company feels chaotic", "we keep having the same…
promote-idea
Converts an album idea from IDEAS.md into an actual album project in one step. Use when the user says "promote [idea title]", "turn idea into album", or "start working on [idea]".
customer-onboarding-and-implementation
Takes a new customer from signature to working — setting a definition of live that both sides agreed before the contract was signed, planning and staffing the implementation, running data migration and integration realistically, training the people who will actually use it, and handing over to the ongoing…
vendor-management
Selects, contracts, and manages suppliers and vendors — requirements, evaluation, negotiation support, onboarding, performance management, and exit. Use this to choose a vendor, run a selection process, structure a service agreement's operational terms, manage an underperforming supplier, plan an exit or migration, or…